DiffusionNet: Discretization Agnostic Learning on Surfaces

Citations Over TimeTop 1% of 2022 papers

Abstract

We introduce a new general-purpose approach to deep learning on three-dimensional surfaces based on the insight that a simple diffusion layer is highly effective for spatial communication. The resulting networks are automatically robust to changes in resolution and sampling of a surface—a basic property that is crucial for practical applications. Our networks can be discretized on various geometric representations, such as triangle meshes or point clouds, and can even be trained on one representation and then applied to another. We optimize the spatial support of diffusion as a continuous network parameter ranging from purely local to totally global, removing the burden of manually choosing neighborhood sizes. The only other ingredients in the method are a multi-layer perceptron applied independently at each point and spatial gradient features to support directional filters. The resulting networks are simple, robust, and efficient. Here, we focus primarily on triangle mesh surfaces and demonstrate state-of-the-art results for a variety of tasks, including surface classification, segmentation, and non-rigid correspondence.

Related Papers

• → A Gluing Method for Non-matching Meshes(2013)1 cited
• → Decomposing Scanned Assembly Meshes Based on Periodicity Recognition and Its Application to Kinematic Simulation Modeling(2010)
• → A Technique for the Long Term Preservation of Finite Element Meshes(2014)
• Wavelet-Based Multi-Resolution Analysis of Irregular Meshes(2007)
• → EFFECTIVE POROSITY OF 3D PRINTED SURGICAL MESHES(2023)